進階搜尋


下載電子全文  
系統識別號 U0026-2308201823100300
論文名稱(中文) 使用空載光達點雲資料於都市區立木偵測
論文名稱(英文) Detection of Individual Tree in Urban Area Using Airborne LiDAR Point Cloud
校院名稱 成功大學
系所名稱(中) 測量及空間資訊學系
系所名稱(英) Department of Geomatics
學年度 106
學期 2
出版年 107
研究生(中文) 黃玫鈺
研究生(英文) Mei-Yu Huang
學號 P66054133
學位類別 碩士
語文別 英文
論文頁數 72頁
口試委員 指導教授-林昭宏
口試委員-許巍嚴
口試委員-徐逸祥
中文關鍵字 空載光達點雲  光達  樹木偵測  都市區域  可適性區域最大值  特徵值分析  邊緣偵測  線偵測  索伯運算子  霍夫轉換  三維分割 
英文關鍵字 LiDAR point cloud  airborne LiDAR  tree detection  urban areas  local maxima filter  eigen analysis  PCA  edge detection  line detection  Sobel operator  Hough transform  3D segmentation 
學科別分類
中文摘要 隨著主動型感測器的增加及量測技術的進步,遙感探測資料及相關方法也隨之發展。多種主動型感測器中,空載光達為目前廣泛應用之技術之一。空載光達可以高效率獲取大範圍測區的高精度地理資訊,因此其相關研究也成為熱門的議題,例如:森林區域的樹木偵測及都市區域的分類問題。由於都市區域的樹木有助於經濟發展、環境及健康問題,且樹木與保育及資產保存議題相關,使用空載光達資料於都市區域進行都市區域的樹木偵測,成為遙感探測應用中相當重要的課題。利用空載光達進行都市區個別樹木偵測及描繪的常見方法,可分為兩個方向:分類導向及分割導向。分類導向著重於萃取特徵,並且將特徵用於分類器的訓練,進而建立一個可分別個別樹木的模型。分割導向分法則著重於資料的幾何資訊,常以二維或是三維幾何資訊進行資料的分割,以達成個別樹木偵測及描繪。然而,運算效率及先驗知識常成為分類導向的問題,分割方法的選擇也為分割導向中優先考量的因素之一。
本研究提出一以資料為導向整合二維及三維的方法,結合分類導向中的特徵萃取及分割導向中的資料分割,進行都市區樹木偵測。本研究主要分為兩個部分:一為二維樹木位置偵測,二為三維樹冠描繪。二維方法主要操作於由三維點雲資料轉換之網格影像,一可適性區域最大值濾波器用以進行區域最大值的偵測,並且記錄區域最大值所在的鄰近範圍。特徵值分析進一步應用於區域最大值及所在鄰近範圍,進行空間結構的辨別,濾除非樹木的區域最大值。但特徵值分析不適用於建物邊界的辨別,因此,邊緣及線特徵也應用於此研究。邊緣及線特徵主要使用索伯運算子及霍夫轉換,以偵測建物邊界線,其結果可用於濾除於建物邊界上的區域最大值。此外,為避免過度偵測,於此研究中,根據樹木生長特性及樹木間的高度和距離關係,建立一套樹木選擇規則,達成更為精確之樹木位置偵測。三維的樹木描繪則以二維方法偵測的樹木位置作為種子點,利用光達點雲資料,結合三維分割、表面區域成長及群聚等原則,建立個別樹木的三維點雲。最後,使用田野調查結果及航拍影像建立參考資料,並以樹木位置為依據,進行偵測成果及參考資料的匹配,完成成果驗證。以本研究所提出的方法應用於偵測區內,成功獲得良好的準確率,並且有效提升運算效率。
英文摘要 Considering the increasing number of active sensors, remote sensing data and related methodologies are assumed to be the most efficient operations. Airborne light detection and ranging (LiDAR) is one of the most common approaches among the various remote sensing techniques. The applications of airborne LiDAR are widely developed, especially for large-area applications such as tree detection in forests or object classification in urban areas. Urban trees can resolve economic, environmental, and health problems, and conservation of trees is important. Therefore, detection of trees using airborne LiDAR data in urban areas is a fundamental topic in recently developed applications. The urban tree detection and delineation method based on airborne LiDAR point cloud can be divided into two main categories: classification-based and segmentation-based methods. The classification-based method focuses on the extraction of features and training of the classifier. Computational efficiency and prior information are generally the critical issues for these methods. For the segmentation-based method, 2D or 3D geometric information is generally used as criteria in data segmentation, and the selected segmentation algorithms are essential.
In this study, an approach that integrates methods with 2D and 3D geometric information for individual tree detection in urban areas is proposed. Furthermore, feature selection and segmentation approaches are adopted in this study. The objective is to detect tree locations and discriminate tree points from other objects in 2D processing and to delineate tree crowns with 3D geometric information. To extract tree apexes and apply feature discrimination, adaptive local maximum (LM) filter and eigen analysis are applied to 2D rasterized images, which is generated from a given 3D point cloud data. Given that eigen analysis is not robust for point cloud on building edges, several edge detection methods are exploited to discriminate LM points between trees and building edges. Furthermore, LM selection schemes are established based on the characteristics of trees and the relationship between tree height and distance. In addition, considering the tree locations, the 3D delineation method using point cloud with the combination of 3D segmentation, surface growth, and clustering is applied. To evaluate the detection results, a set of matching procedures are performed with the aid of field inventory data and aerial image. The proposed algorithm results in an excellent extraction and matching rate, and the analysis of the detection results is conducted according to the defined evaluation criteria.
論文目次 摘要 I
Abstract III
List of Table IX
List of Figure IX
Chapter 1 Introduction 11
Chapter 2 Related Work 17
2.1 Classification-based method 17
2.2 Segmentation-based method 19
Chapter 3 Methodology 21
3.1 System Workflow 21
3.2 Data Preprocessing 22
3.2.1 Data Transformation 24
3.2.1.1 Image Spatial Resolution 24
3.2.1.2 Data Interpolation 25
3.2.2 Ground-point filter 27
3.3 2D Tree Detection 29
3.3.1 Adaptive Local Maxima (LM) Filter 31
3.3.2 Eigen Analysis 33
3.3.3 Edge and Line Detection 36
3.3.4 LM Selection 40
3.4 3D Tree Delineation 45
Chapter 4 Experimental Results and Discussion 47
4.1 Test data and study area 47
4.2 Detection Evaluation 48
4.2.1 Ground Truth and Detection Results 49
4.2.2 Tree Matching Procedure 50
4.2.3 Evaluation Criteria 52
4.3 Validation of Detection and Matching Procedure 53
4.4 Validation of Adaptive Local Maxima Filter 53
4.5 Validation of Iterative Scheme in 2D Detection 55
4.6 Determination of Eigen Features 57
4.7 Validation of Local Maxima Selection Scheme 60
4.8 Validation of a Test Area 64
4.9 3D Delineation 65
Chapter 5 Conclusions and Future Work 66
Reference 68
參考文獻 Brodu, N., Lague, D.. "3D terrestrial lidar data classification of complex
natural scenes using a multi-scale dimensionality criterion: applications in geomorphology ." ISPRS J. Photogramm. Remote Sens., 68, pp. 121–134,2012.
Bienert, A., Scheller, S., Keane, E., Mohan, F. and Nugent, C.. "Tree
detection and diameter estimations by analysis of forest terrestrial laserscanner point clouds." ISPRSWorkshop on Laser Scannig 2007 and SilviLaser 2007 Espoo Finland Commission(WG V/3), pp. 50–55, 2007.
Coops, N. C., Hilker, T., Wulder, M. A., St-Onge, B., Newnham, G. J.,
Siggins, A., & Trofymow, J. A.." Estimating canopy structure of Douglas-fir forest stands from discrete-return LiDAR." Trees-Structure and Function, 21(3), pp. 295–310, 2007.
Chen, Q., Baldocchi, D., Gong, P., & Kelly, M.. "Isolating individual trees
in a savanna woodland using small footprint lidar data."
Photogrammetric Engineering &Remote Sensing, 72(8), pp.
923−932, 2006.
Chen, L. C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A. L..
"Semantic image segmentation with deep convolutional nets and fully
connected CRFs." In Proc. Int. Conf. Learning Representations, 2015.
Eysn, L., Hollaus, M., Lindberg, E., Berger, F., Monnet, J., Dalponte, M.,
Kobal, M., Pellegrini, M., Lingua, E., Mongus, D., et al. "A benchmark of LiDAR-based single tree detection methods using heterogeneous forest data from the Alpine space." Forests, 6, 1721–1747, 2015.
Gupta, S., Mazumda, S. G., " Sobel Edge Detection Algorithm."
International Journal of Computer Science and Management Research, Vol 2, Issue 2, 2013.
Gorte, B., Oude Elberink, S., Sirmacek, B., Wang, J.. "IQPC 2015 Track:
Tree separation and classification in mobile mapping lidar data." Int.
Arch. Photogramm. Remote Sens. Spat. Inf. Sci., XL-3/W3, pp. 607–
612, 2015.
Hyyppä, J.; Holopainen, M.; Olsson, H.. "Laser Scanning in Forests."
Remote Sens., 4, pp. 2919–2922, 2012.
Holopainen, M., Vastaranta, M., Kankare, V., Hyyppä, J., Liang, X., Litkey,
P., Yu, X., Kaartinen, H., Kukko, A., Kaasalainen, S., Hyyppä, H. Vaaja, M., Jaakkola, A.. "The use of ALS, TLS and VLS measurements in mapping and monitoring urban trees." Urban Remote Sensing Event (JURSE), pp. 29-32, 2011.
Hecht, R., Meinel, G., and Buchroithner, M. F.. “Estimation of urban green
volume based on single-pulse LiDAR data.” IEEE Trans. Geosci. Remote Sens., vol. 46, no. 11, pp. 3832–3840, 2008.
Höfle, b., Hollaus, M., Hagenauer, J.. “Urban vegetation detection using
radiometrically calibrated small-footprint full-waveform airborne LiDAR data,” ISPRS J. Photogramm. Remote Sens., vol. 67, pp. 134–147, 2012.
Hackel, T., Wegner, J.D., Schindler, K.. "Fast semantic segmentation of 3D
point clouds with strongly varying density." ISPRS Ann. Photogramm.
Remote Sens. Spat. Inf. Sci, III-3, pp. 177–184, 2016.
Jensen, J. L. R., Humes, K. S., Vierling, L. A., Hudak, A.T.. " Discrete
return lidar-based prediction of leaf area index in two conifer forests."
Remote Sensing of Environment, vol.112, pp. 3947-3957, 2008.
Jarzgbek-Rychard, M.; Borkowski, A.. "3D building reconstruction from
ALS data using unambiguous decomposition into elementary structures." ISPRS J. Photogramm. Remote Sens, pp. 1–12, 2016.
Kelly, M.. "Urban trees and the green infrastructure agenda." In
Proceedings of the Urban Trees Research Conference, 13–14, pp.166–180, 2011.
Krizhevsky, A., Sutskever, I., Hinton, G. E., " ImageNet Classification with
Deep Convolutional Neural Networks." In NIPS, 2012.
Lee, I.; Schenk, T.. " Perceptual organization of 3D surface points." Int.
Arch. Photogramm. Remote Sens. Spat. Inf. Sci., XXXIV-3A, pp. 193–198, 2002.
Lindenbergh, R C., Berthold, D., Sirmacek, B., Wang, J., Ebersbach, D..
"Automated large scale parameter extraction of road-side trees
sampled by a laser mobile mapping system." In Proceedings of the International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, ISPRS Geospatial Week, 2015.
Monnet, J.M., Mermin, E., Chanussot, J., Berger, F.. "Tree Top Detection
Using Local Maxima Filtering: A Parameter Sensitivity Analysis." In Proceedings of 10th International Conference on LiDAR Applications for Assessing Forest Ecosystems (Silvilaser 2010), Freiburg, Germany, 14–17, pp. 9,2010.
Maltamo, M., Næsset, E., Vauhkonen, J.. "Forestry Applications of
Airborne Laser Scanning: Concepts and Case Studies. Series: Managing Forest Ecosystems." Vol. 27, pp. 464, 2014.
Monnier, F., Vallet, B., Soheilian, B.. "Trees detection from laser point
clouds acquired in dense urban areas by a mobile mapping system." ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., I-3, pp. 245–250, 2012.
Oshio, E., Asawa, T., Hoyano, A., Miyasaka, S.. "Estimation of tree crown
structure in urban areas using high resolution airborne LiDAR." IEEE
International Geoscience and Remote Sensing Symposium (IGARSS),
pp. 2145 –2148, 2011.
Plowright, A.. "Extracting trees in an urban environment using airborne
LiDAR." GSS cIRcle Open Scholar Award (UBCV Non-Thesis Graduate Work), 2015.
Popescu, S. C., Zhao, K. G.. "A voxel-based lidar method for estimating
crown base height for deciduous and pine trees." Remote Sensing of
Environment, 112(3), pp. 767−781, 2008.
Song, C., Dickinson, M.B., Su, L., Zhang, S., Yaussey, D.. "Estimating
average tree crown size using spatial information from Ikonos and QuickBird images: Across-sensor and across-site comparisons." Remote Sens. Environ., 114, pp. 099–1107, 2010.
Schreyer, J., Tigges, J., Lakes, T., Churkina, G.. " Using Airborne LiDAR
and QuickBird Data for Modelling Urban Tree Carbon Storage and Its Distribution—A Case Study of Berlin." Remote Sens., 6(11), pp. 10636-10655, 2014.
Wilson, J. P.. "Digital terrain modeling." Geomorphology, 137(1), pp. 107-
121, 2012.
Wang, L., Gong, P., Biging,G.S.. "Individual tree-crown delineation and
treetop detection in high-spatial-resolution aerial imagery. Photogramm. Eng. Remote Sens., 70, 351–357, 2004.
Weinmann, M., Weinmann, M., Mallet, C., Brédif, M.. " A classification-
segmentation framework for the detection of individual trees in dense MMS point cloud data acquired in urban areas." Remote Sens., 9(3), 277, 2017.
Weinmann, M., Jutzi, B., Hinz, S., Mallet, C.. "Semantic point cloud
interpretation based on optimal neighborhoods, relevant features and efficient classifiers." ISPRS J. Photogramm. Remote Sens., 105, pp. 286–304, 2015.
West, K.F., Webb, B.N., Lersch, J.R., Pothier, S., Triscari, J.M., Iverson,
A.E.. "Context-driven automated target detection in 3-D data." Proc. SPIE, 5426, pp. 133–143, 2004.
Wu, B., Yu, B., Yue, W., Shu, S.; Tan, W., Hu, C., Huang, Y., Wu, J., Liu,
H.. "A voxel-based method for automated identification and
morphological parameters estimation of individual street trees from mobile laser scanning data." Remote Sens., 5, pp. 584–611,2013.
Yao, W.; Wei, Y.. "Detection of 3-D individual trees in urban areas by
combining airborne LiDAR data and imagery." IEEE Geoscienc., 2013.
Zhen, Z., Quackenbush, L. J., Zhang, L.. " Trends in Automatic Individual
Tree Crown Detection and Delineation—Evolution of LiDAR Data."
Remote Sens., 8(4), pp. 333, 2016.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2020-07-27起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2020-07-27起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw